Comorbidities - cases in which patients have two or more chronic conditions - impose burden on the health care system as well as society. Causal relationships and interaction among different diseases in the comorbidity set is complex, and not yet completely understood by the medical community. Understanding the causality between diseases is an essential element of science of medicine. Patient treatment would also be more efficient if better knowledge of causality was available. There are different approaches to shed more lights on causality in medicine. In this article, we propose two approaches. One is using statistical causal inference algorithms on electronic medical data to identify potential causal relationships among diseases. In the second approach, we use qualitative modeling techniques to build models of disease mechanisms. Each one of these directions has its own pitfalls. The assumption is integrating the two approaches will minimize the drawbacks of each. The integration involves using qualitative models of underlying disease mechanisms to evaluate and explain the potential causal relationships resulted from the causal inference algorithms. This integration is complex, and require big effort from the community. In this article, we are proposing new research direction based on our preliminary work.

For more effective collaboration, users and autonomous systems should interact naturally. We propose that sketch-based interaction coupled with qualitative representations and analogy provides a natural interface for users and systems. We introduce comic graphs that capture tasks in terms of the temporal dynamics of the spatial configurations of relevant objects. This paper demonstrates, through a strategy simulation example, how these models could be learned by demonstration, transferred to new situations, and enable explanations.

This paper presents results of analysis performed on a physiologic time-series dataset that was collected from a wearable ECG monitoring system worn by individuals who suffer from panic disorder. Models are constructed and evaluated for distinguishing between pathologic and non-pathologic states, including panic (during panic attack), pre-panic (preceding panic attack) and non-panic (outside panic attack window). The models presented use data fusion to combine both traditional time and frequency domain heart rate variability analysis together with nonlinear/complexity analysis. The best performing model is shown to be a random forest classifier that achieves an accuracy of 97.2% and 90.7% for recognizing states of panic and pre-panic , respectively. The models presented have application in pervasive and ubiquitous mobile and wearable health management systems.

Patients with multiple health conditions pose significant challenges for modern healthcare. Understanding if and how these conditions are linked is essential to providing effective treatment. Physicians and researchers create explanatory models to develop hypotheses for these connections. In this paper, we discuss the breadth of domains these explanations draw upon as well as the diversity of applications of these models. Throughout the paper, we use example explanatory models from published literature and discuss the state-of-the-art of knowledge representation to support clinicians.

Members of effective teams must have knowledge about each others future actions. Typically, this is done through messages or precomputed divisions of labor. The former requires ongoing communication between the agents and the latter constrains the autonomy of the individual agents. We introduce coordination rules that facilitate collaboration between autonomous agents when communication is lost. By envisioning the results of all possible plan executions for each agent, we identify which decisions result in the greatest increase of within-team uncertainty. If removing this action does not significantly reduce the expected utility of the plan, we create a coordination rule, a statement that the agent will or will not take a particular action in some possible future. Coordination rules facilitate collaboration by improving state estimation and prediction by teammates. To accomplish this, we make the following contributions. First, we identify qualitative interactions by representing the space of decisions made by the agents in plan-with-options and their consequences in a factored envisionment that compactly represents multi-agent simulations. Second, we define two classes of within-team uncertainty metrics with respect to the envisionment. Third, we present an evaluation of the effects of coordination rules on action selection in three scenarios. In all three scenarios, coordination rules enabled extended planning horizons and reduced planning times with no significant effect on plan quality.

In this paper, we present first steps towards a mobile and wearable system intended to help people who experience regular and spontaneous panic attacks due to panic disorder. The goal of the system is to predict oncoming panic attacks and to deliver in-the-moment interventions on a smartphone device. Interventions are intended to reduce symptom severity by enabling a user to respond to approaching panic episodes. An initial feasibility study is described where a small real-world data set was collected. Personalized prediction models were trained which take, as input, physiological data and output a binary classification of either pre-panic or non-panic. We demonstrate proof-of-concept of episode prediction on this small dataset.

Panic disorder is a serious condition that affects approximately six million adults in the United States per year. Reducing the severity of panic attack symptoms would allow a better quality of life for panic attack sufferers. This paper presents steps towards a mobile and wearable system that aims to help reduce the severity of symptoms experienced by individuals with this condition. The system provides a way to continuously monitor the physiological data of an individual via a wearable device. Users are able to report when panic attacks take place, along with a rating of the severity of symptoms experienced. Reported episodes provide ground truth data to build panic prediction models. The eventual goal of the system is to make predictions about approaching panic attacks and to deliver interventions that help the individual to cope with the approaching episode. We describe a mobile-based intervention that has been developed, which instructs the individual to perform breathing and relaxation exercises. Presently, the system has been utilized in a small pilot study where 10 individuals who suffer from panic disorder reported 29 panic attacks while collecting physiological data, along with the severity of symptoms. We found that out of 15 symptoms the ones with high severity reported were anxiety, worry and shortness of breath. Furthermore, physiological differences were observed between panic and non-panic intervals.

When a computer system is hacked, analyzing the root-cause (for example entry-point of penetration) is a diagnostic process. An audit trail, as defined in the National Information Assurance Glossary, is a securityrelevant chronological (set of) record(s), and/or destination and source of records that provide evidence of the sequence of activities that have affected, at any time, a specific operation, procedure, or event. After detecting an intrusion, system administrators manually analyze audit trails to both isolate the root-cause and perform damage impact assessment of the attack. Due to the sheer volume of information and low-level activities in the audit trails, this task is rather cumbersome and time intensive. In this position paper, we discuss our ideas to automate the analysis of audit trails using machine learning and model-based reasoning techniques. Our approach classifies audit trails into the high-level activities they represent, and then reasons about those activities and their threat potential in real-time and forensically. We argue that, by using the outcome of this reasoning to explain complex evidence of malicious behavior, we are equipping system administrators with the proper tools to promptly react to, stop, and mitigate attacks.

For impact in industrial settings, qualitative reasoning techniques must work with existing modeling languages and libraries. This paper presents an important subproblem that must be solved to perform qualitative simulation with industry models, the problem of initialization of systems of hybrid discrete and algebraic equations. We present a case study using five models illustrating the scope of the problem, and then we present three examples of inconsistencies that may arise when guiding the initialization approach with the results of quantitative simulation. We discuss our approach to alleviate these problems in an effort to initialize a very large system model. We close with a discussion of related and future work.

Modelica models are typically used for simulation to investigate properties of a possible system designs. This is often done manually or combined with optimization to select the best design parameters.

We propose a model-based diagnosis framework in which Modelica models of faulted behavior are used in combination with a Bayesian approach. The fault augmented models are automatically generated through a process developed as part of our Fault Augmented Model Extension (FAME) work. Fault diagnosis using a Bayesian approach is based on computing a set of probability density functions, a process that is usually intractable for any reasonably complex system. We use Approximate Bayesian Computation (ABC) to bound the numerical and computational complexity. The basic idea is to use fault augmented Modelica models to create probability distributions of possible outcomes and then compare those distributions against actual observations to perform parameter estimation. The detection of faults is treated as a model selection problem and the inference of their severity levels is treated as parameter estimation. The diagnostic precision of this approach is evaluated on a Modelica vehicle drive line model.

To minimize the design cost of a complex system and maximize performance, a design team ideally must be able to quantify reliability and mitigate risk at the earliest phases of the design process, where 80% of the cost is committed. This paper demonstrates the capabilities of a new System Reliability Exploration Tool based on the improved simulation capabilities of a system called Fault-Augmented Modelica Extension (FAME). This novel tool combines concepts from FMEA, traditional Reliability Analysis, and Quality Engineering to identify, gain insight, and quantify the impact of component failure modes through time evolution of a system's lifecycle. We illustrate how to use the FAME System Reliability Exploration Tool through a vehicle design case study.

Engineers need to perform many different types of analyses as they design systems.Modelica has become a leading language to support numerical simulation.As a consequence there is widespread understanding of Modelica and a large number of Modelica model libraries available.This paper addresses the task of using formal methods to derive system properties such as whether a design meets its requirements for all possible inputs.We report on our experience building a qualitative reasoner operating on Modelica models.In this paper, we highlight five Modelica modeling practices that impede the application of formal methods.

Qualitative reasoning can play an important role in early stage design. Currently, engineers explore the design space using simulation models built in languages such as Modelica. To make qualitative reasoning useful to them, designs specified in their languages must be translated into a qualitative modeling language for analysis. The contribution of this paper is a sound and effective mapping between Modelica and qualitative reasoning. To achieve a sound mapping, we extend envisioning, the process of generating all relevant qualitative behaviors, to support Modelica's declarative events. For an effective mapping, we identify three classes of additional constraints that should be inferred from the Modelica representation thereby exponentially reducing the number of unrealizable trajectories. We support this contribution with examples and a case study.